Commit Graph

406 Commits

Author SHA1 Message Date
Tong Li
54a08bde29
examples : add whisper.android.java for compatibility with older Android versions using Java (#1382)
* save the recorded audio to a file

* Alignment -help

* Save the correct audio

* chage to a consistent coding style

* Correct typo

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Correct variable misuse

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* add *.bin .cxx/ .gradle/ cmake-build-debug/ to gitignore

* add whisper.android.java

* Added support for older versions of Android of Java

* add examples for android java

* add README.md for android java

* add fullTranscribeWithTime

* 增加 toString()方法和测试

* change return type to void

* update to v1.4.1

* add WhisperService

* chage to whisper_full_get_segment_t1

* add method transcribeDataWithTime

* modified toString
```
return "[" + start + " --> " + end + "]:" + sentence;
```

* Optimize code logic

* update text view on handle

* set max lines

* change Chinese to English

* Update bindings/java/build.gradle

* Update .gitignore

* add android.java to github action

* chage android.java to   android_java in build.yml

* remove gradle

* chage jdk to temurin in android_java of CI

* chage jdk to temurin 11 in android_java of CI

* add x to gradlew

* set api-level for android_java of CI

* Update examples/whisper.android.java/app/src/main/jni/whisper/CMakeLists.txt

* add ndk version in build.gradle

* remove local.properties

* add testFullTranscribeWithTime

---------

Co-authored-by: litongmacos <litongjava@qq.com>
Co-authored-by: bobqianic <129547291+bobqianic@users.noreply.github.com>
2023-11-12 18:31:58 +02:00
Georgi Gerganov
b0502836b8
whisper : add full CUDA and Metal offloading (#1472)
* whisper : migrate to ggml-backend

* whisper : fix logit reading

* whisper : fix tensor allocation during load

* whisper : fix beam-search with CUDA

* whisper : free backends + fix compile warning

* whisper : print when CUDA is enabled

* whisper : fix CoreML

* make : clean-up

* talk : fix compile warning

* whisper : support ggml_conv with CUDA and Metal (#1473)

* ggml : add CUDA support for ggml_conv

* whisper : remove ggml_repeat for conv bias + single backend

* cuda : fix im2col kernel

* metal : add im2col support + mul mat-vec f16 x f16

* bench-all : add q4 models

* whisper : clean-up

* quantize-all : fix

* ggml : im2col opts

* whisper : avoid whisper_model_data wrapper

* whisper : add note that ggml_mul_mat_pad does not work with CUDA

* whisper : factor out graph compute in common function

* whisper : fixes

* whisper : fix UB with measure buffers

* whisper : try to fix the parallel whisper_state functionality (#1479)

* whisper : try to fix the parallel whisper_state functionality

* whisper : fix multi-state Metal

* whisper : free backend instances in whisper_state
2023-11-12 15:31:08 +02:00
Jakub Ráček
37947203e6
talk-llama : add language auto detect (#1467)
* Add '-l auto' to talk-llama example

* Update examples/talk-llama/talk-llama.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-11-09 19:21:44 +02:00
Sindre Sorhus
d03c60dd7f
ios : add support for Swift Package Manager (#1370)
* Add support for Swift

* Make it build in Xcode

* Use the SPM package in the SwiftUI example app
2023-11-07 23:53:31 +02:00
Georgi Gerganov
2cdfc4e025
whisper : add support for large v3 (#1444)
* whisper : add support for large v3

* bench : fix build + fix go bindings

* bench : fix n_mels

* models : update readme
2023-11-07 15:30:18 +02:00
Tobrun
973111088b
android : decouple example into a library and app module (#1445) 2023-11-07 14:27:33 +02:00
Georgi Gerganov
b629d2d4fe
cmake : fix talk-llama build 2023-11-07 11:03:21 +02:00
Jhen-Jie Hong
75dc800d21
talk-llama : fix n_gpu_layers usage again (#1442) 2023-11-07 10:51:27 +02:00
Jhen-Jie Hong
3989b29a9b
examples : fix n_gpu_layers usage in talk-llama (#1441) 2023-11-07 01:36:23 +00:00
Jhen-Jie Hong
0463028bc2
whisper : add context param to disable gpu (#1293)
* whisper : check state->ctx_metal not null

* whisper : add whisper_context_params { use_gpu }

* whisper : new API with params & deprecate old API

* examples : use no-gpu param && whisper_init_from_file_with_params

* whisper.objc : enable metal & disable on simulator

* whisper.swiftui, metal : enable metal & support load default.metallib

* whisper.android : use new API

* bindings : use new API

* addon.node : fix build & test

* bindings : updata java binding

* bindings : add missing whisper_context_default_params_by_ref WHISPER_API for java

* metal : use SWIFTPM_MODULE_BUNDLE for GGML_SWIFT and reuse library load

* metal : move bundle var into block

* metal : use SWIFT_PACKAGE instead of GGML_SWIFT

* style : minor updates

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-11-06 11:04:24 +02:00
Georgi Gerganov
f96e1c5b78
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)
* sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.)

* metal : allow env metal variable to override resource path (#1415)

* Allow env variable to override resource path

* Update ggml-metal.m

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* sync : restore common / main from `master`

* sync : restore whisper from `master`

* talk-llama : update to latest llama.cpp

* ruby : fix build

* ggml : fix 32-bit ARM build

* ggml : fix MIN / MAX macro collisions + update ios bindings

* ggml : fix ifdefs and MIN / MAX again

* exampels : fix Obj-C and Swift examples

* ggml : fix 32-bit ARM compatibility

* ggml : one more attempt to fix 32-bit ARM compat

* whisper : fix support for larger graphs

---------

Co-authored-by: Chris Raethke <codesoda@users.noreply.github.com>
2023-11-03 21:35:05 +02:00
Asad Memon
d445098c8f
talk-llama : move up-to-date demo to top (#1417) 2023-11-02 18:50:13 +02:00
Georgi Gerganov
74de25158e
talk-llama : add an up-to-date demo video 2023-11-02 15:28:48 +02:00
Aarni Koskela
bce49a260e
examples : Implement JSON output for Token-Level data in main (#1358) 2023-10-31 19:54:52 +00:00
ai-at-home
dfe4bc6e59
README : Update README in stream to clarify where to compile from (Issue #1400)
* Clarify doc about where to compile from

* Update examples/stream/README.md

* Update examples/stream/README.md

* Update README.md

---------

Co-authored-by: AI @ Home <>
Co-authored-by: bobqianic <129547291+bobqianic@users.noreply.github.com>
2023-10-29 17:11:13 +00:00
mkiol
940cdb1396
whisper : abort callback improvements (#1345)
* whisper : initialize abort_callback to null

* whisper : add example how to use abort_callback
2023-10-08 17:22:24 +03:00
bobqianic
08fa34882f
examples : move wav_writer from stream.cpp to common.h (#1317)
* Allocate class on the stack instead of on the heap

* Add class wav_writer

* fix some minor issues

* fix some minor issues

* remove potential misleading API
2023-10-03 22:56:11 +03:00
brunofaustino
c76c11e59c
examples: Update the README for Talk - fixing the gpt2 URL (#1334) 2023-10-01 04:21:32 +08:00
litong
707507ff6d
Examples: Add save audio to file option in stream.cpp (#1310)
* save the recorded audio to a file

* Alignment -help

* Save the correct audio

* chage to a consistent coding style

* Correct typo

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Correct variable misuse

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

---------

Co-authored-by: bobqianic <129547291+bobqianic@users.noreply.github.com>
2023-09-22 23:43:21 +08:00
Evgeny Kuznetsov
700f63a806
bench: fix missing include <cstring> (#1303) 2023-09-18 15:51:10 +08:00
Georgi Gerganov
1ca4041b86
talk-llama : update to latest llama.cpp 2023-09-15 20:06:31 +03:00
Georgi Gerganov
93935980f8
whisper : Metal and ggml-alloc support (#1270)
* metal : init

* whisper : factor out graph builds

* whisper : allocate encoder and decoder using ggml-alloc

* whisper : ggml-alloc is now supported

* whisper : CoreML support ggml-alloc

* build : fix ggml-alloc

* ios : update submodule

* extra : update sync-ggml.sh script to also sync ggml-alloc

* ci : see if this is causing the crash

* whisper : refactor ggml-alloc init

* whisper.android : try to fix build

* whisper : initial Metal version

* ci : try to debug vmem issue

* metal : decoder works on GPU!

* metal : add multi-decoder support

* ggml : fix ggml_nbytes (probably temp solution)

* metal : run "cross" step on the GPU

* whisper : remove ggml_repeat in the encoder

* whisper : offload the Encoder to Metal

* ggml : use simpler ggml_bytes() implementation

* ggml-alloc : try to make CI happy by reducing vram to 128GB

* whisper : add whisper_allocr to wrap ggml_allocr

* whisper : factor out alloc init in a function

* cmake : update to support Metal build

* whisper : add <functional> header

* objc : fix build (no Metal yet)

* ios : add Metal support

* swiftui : fix build

* metal : speed-up KQ multiplication

* metal : sync latest llama.cpp kernels

* readme : add Metal info

* ios : update submodule

* coreml : add code to toggle Core ML config (CPU, ANE, GPU)

* bench : fix timings by running a pre-heat

* bench : start benching the decoder

* whisper : add ggml_mul_mat_pad

* bench : fix uninitialized vars

* whisper : add comment for disabling mul-mat padding

* whisper : add description of ggml_mul_mat_pad

* whisper : clean-up ggml_mul_mat_pad

* metal : remove the "concurrent" flag

* bench : variable n_past

* ios : update SPM package
2023-09-15 12:18:18 +03:00
Przemysław Pawełczyk
b55b505690
build : do not use _GNU_SOURCE gratuitously (#1129)
* Do not use _GNU_SOURCE gratuitously.

What is needed to build whisper.cpp and examples is availability of
stuff defined in The Open Group Base Specifications Issue 6
(https://pubs.opengroup.org/onlinepubs/009695399/) known also as
Single Unix Specification v3 (SUSv3) or POSIX.1-2001 + XSI extensions,
plus some stuff from BSD that is not specified in POSIX.1.

Well, that was true until NUMA support was added recently in ggml,
so enable GNU libc extensions for Linux builds to cover that.

There is no need to penalize musl libc which simply follows standards.

Not having feature test macros in source code gives greater flexibility
to those wanting to reuse it in 3rd party app, as they can build it with
minimal FTM (_XOPEN_SOURCE=600) or other FTM depending on their needs.

It builds without issues in Alpine (musl libc), Ubuntu (glibc), MSYS2.

* examples : include SDL headers before other headers

Avoid macOS build error when _DARWIN_C_SOURCE is not defined, brought by
SDL2 relying on Darwin extension memset_pattern4/8/16 (from string.h).

* make : enable BSD extensions for DragonFlyBSD to expose RLIMIT_MEMLOCK

* make : use BSD-specific FTMs to enable alloca on BSDs

* make : fix OpenBSD build by exposing newer POSIX definitions

* cmake : follow recent FTM improvements from Makefile
2023-09-07 12:36:14 +03:00
Georgi Gerganov
2818de21ff
examples : fix build + compile warnings (close #1256) 2023-09-07 12:33:12 +03:00
Digipom
afa5477d1c
whisper.android : bump gradle plugin and dependencies + a lint pass (#1255) 2023-09-07 12:15:59 +03:00
Digipom
f990610776
whisper.android : address ARM's big.LITTLE arch by checking cpu info (#1254)
Addresses https://github.com/ggerganov/whisper.cpp/issues/1248
2023-09-06 18:32:30 +03:00
Georgi Gerganov
59a3d0cb57
ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220)
* ggml : sync (ggml-alloc, GPU, eps, etc.)

* ggml : fix build

* wasm : fix build
2023-09-05 13:54:40 +03:00
Jhen-Jie Hong
99d3c105f5
whisper.android : fix cmake multiple libraries build (#1224)
* whisper.android : fix multiple libraries build

* fix flags for default target
2023-08-30 14:45:13 +03:00
AustinMroz
175ffa64ee
examples : vim plugin and LSP server (#1144)
* Initial proof of concept Vim plugin

At present, this is likely only slightly better than feature parity with
the existing whisper.nvim

Known issues:
 Trailing whitespace
 Up to an existing length(5 seconds) of speech may be processed when
  listening is enabled
 CPU cycles are spent processing speech even when not listening.

Fixing these issues is likely dependent upon future efforts to create a
dedicated library instead of wrapping examples/stream

* Support $WHISPER_CPP_HOME environment variable

A minor misunderstanding of the whisper.nvim implementation resulted in
a plugin that was functional, but not a drop in replacement as it should
be now.

* Initial progress on LSP implementation

Libcall is nonviable because the library is immediately freed after a
call is made. Further investigation has shown Language Server Protocol as
a promising alternative that both simplifies the required logic on the
vimscript side and increases the ease with which plugins for other
editors could be made in the future. This is a very large undertaking
and my progress has slowed substantially.

Work is far from being in a usable state, but I wish to keep track of
major refactors for organizational purposes.

* Rewrite audio windowing of guided transcription

One of the defining goals of this venture is allowing consecutive
commands to be rattled off without the existing deadzones of the current
implementation.

* Add unguided_transcription. Cleanup.

The unguided transcription implantation heavily borrows from existing
example implementations and the guided_transcription logic.

A high level pass was done to check that method arguments are accurate
to what inputs are actually required.

A first attempt at cancellation support was added for record keeping,
but will be deleted in a future commit.

* Fix compilation.

Resolves a large number of compilation errors.
No testing has been done yet for execution errors.

Update Makefile and .gitignore

* Functional unguided_transcription

* Functional guided_transcription

Fix commandset_list being passed by value
Properly register the first token of a multitoken command

* Minor changes before time fix

I've apparently made an awfully major mistake in thinking that unix time
was in milliseconds and will be changing all timekeeping code to use
standardized methods.

In preparation for this is a number of minor bugfixes.
Output is manually flushed.
An echo method has been added.
registerCommandset now wraps the returned index

* Swap timekeeping to use std::chrono

* Add work in progress lsp backed whisper.vim plugin

Current progress blockers are
 Adding modality awareness to the command processing
  (specifically, motion prompting)
 Improving the VAD to be a little more responsive
  (testing start of activity)

* Reworked vim plugin command loop

* Fix change inside

Multiple bug fixes that, crucially, bring the plugin to the point where a
demonstration video is possible

Add better echo messaging so whisper_log isn't required
 Add loading complete message as indicator when listening has started
Insert/append are actually included in command sets
Some more heavy handed corrections to prevent a double exit when leaving
insert mode
As a somewhat hacky fix, the very first space is removed when inserting.
 This cleans up most use cases, but leaves me unsatisfied with the few
 cases it would be desired.

* Forcibly set commandset_index to 0 after subinsert

Also remove unnecessary ! to use builtin vim command

* Fix upper

A minor scope mistake was causing upper'd inputs to be eaten.
This was fixed and echoing was slightly improved for clarity.

* Fix formatting

Corrects indentation to 4 spaces as project standard
Slightly better error support for malformed json input

* Remove obsolete vim plugin

* Add json.hpp library

The same library that is used for the llama.cpp server

* Minor cleanups

add lsp to the make clean directive.
remove a redundant params definition.
reorder whisper.vim logging for subtranscriptions
Corrections to unlets (variables of argument scope appear immutable)

* Fix indentation. Fallback for subTranscription

Indentation has been changed to 4 spaces.

Unit testing has been set up, I'm opting not to include it in the
repository for now.
It however, has revealed a bug in the state logic where a
subtranscription can be initiated without having a saved command
When this occurs, append is added as a fallback

* Move audio polling logic to a subfunction

While work on the improved vad will continue, It's grown to be a little
out of scope. Instead, a future commit will perform multiple detection
passes at substretches of audio when a backlog of audio exists.

To facilitate this, and prevent code duplication, the vad code has been
moved into a subfunction shared by both the unguided and guided
transcription functions.

* Test for voice over subchunks if backlog > 1s

As the existing VAD implementation only checks for a falling edge at the
end of an audio chunk. It fails to detect voice in cases where the
recorded voice is only at the beginning of the audio.

To ameliorate this, when the timestamp would cause analysis of audio
over a second in length, it is split into 1 second length subchunks
which are individually tested.

Results are promising, but there seems to be a remaining bug with
unguided transcription likely related to saving context

* Limit the maximum length of audio input.

This existing VAD implementation only detects falling edges, which
means any gap in the users speaking is processed for transcription.
This simply establishes a constant maximum length depending on the type
of transcription. Uguided gets a generous 10 seconds and guided, 2.

While quick testing showed that commands are generally around a half a
second to a second, limiting commands to an even second resulted in
extreme degradation of quality. (Seemingly always the same output for a
given commandset)

* Unguided timestamp tracking, cleanup

Unguided transcriptions where not setup to allow for passing of
timestamp data forward, but have been corrected.

No_context is now always set to false. While conceptually desirable for
the quality of guided transcription, It was seemingly responsible for
prior command inputs ghosting in unguided transcription.

Save and Run are now tracked by command number instead of command text.
While command_text was provided for convenience, I wish to keep command
index authoritative. This gives greater consistency and potentially
allows for end users to rename or even translate the spoken versions of
these commands

* By default, maintain mode.

Previously, mode was reset to 0 unless otherwise set.
In addition to causing some edge cases, this was didn't mesh well with
the existing approach to visual mode.

With this change, initial tests indicate visual mode is functional.

* Add undo breaks before subtranscriptions

Subtranscriptions use undo as a hack to allow for partial responses to
be displayed. However, scripts don't cause an undo break mid execution
unless specifically instructed to. This meant that multiple
unguided transcriptions from a single session would cause a latter to
undo a former.

This is now fixed and undo should be reasonably usable as a command.

* Append instead of insert for new undo sequence

When entering and leavening insert mode with `i`, the cursor shifts one
column to the left. This is remedied by using append instead of insert
for setting these breaks in the undo sequence

`-` was also added to the pronunciation dictionary to be pronounced as
minus as it was causing a particularly high failure rate.

* Move undo sequence breaks to command execution

Previously, undo sequence breaks were triggered when there was a command
that caused a move to insert mode. This caused commands that changed
state (like delete or paste) to be bundled together with into the last
command that caused text to be entered.

* Fix repeat. Add space, carrot, dollar commands

 Repeat (.) wasn't being tracked properly just like undo and is being
 manually tracked now.

 While efforts have been made to properly handle spaces, it was
 particularly finicky to add a single space when one is needed. A
 special 'space' command has been added to insert a single space and move
 the cursor after it.

 Carrot and Dollar commands have been added for start of line and end of
 line respectively. These are both simple to implement, and just a
 matter of defining a pronunciation.

* Return error on duplicate in commandset

Not every command in the commandset tokenizes to a single token.
Because of this, it's possible for that two commands could resolve to
the same single token after subsequent tokens are discarded.

This commit adds a simple check for duplicates when a commandset is
registered and returns an error if so.

Additional code will be required later on the vim side to actually
process this error.

* Add support for user-defined commands

This adds a user definable dictionary from spoken keys to strings or
funcrefs. All keys are added to the commandlist and when spoken, trigger
the corresponding function.

Like "save" and "run", these user commands are only available when the
command buffer is empty.

* Add readme, update cmake

* Add area commandset. Refactor spoken_dict

Area commands (inside word, around sentence...) have been given a
commandset as considered earlier.

Verbose definitions for spoken_dict entries now use dicts instead of
lists. This shortens the definition for most keys that require it and
scales better with the addition of further commandsets

* Add mark, jump. Fix change under visual.

Mark (m) and jump (') have been added.

When a visual selection was executed upon a command that initiated a
subtranscription (change) the area of the visual selection is not
properly tracked which causes the attempt to stream in partial response
to fail. This is solved by disabling partial transcriptions from being
streamed when a subtranscription is started while in visual mode.

* Accommodate ignorecase. Fix change.

From testing on older different versions of vim, the test for
distinguishing an 'R' replace all from an 'r' replace could fail if
ignorecase was set. The comparison has been changed to explicitly
require case matching

Change detection has been moved to the execution section as it was missing the
change+motion case.

* Support registers. Fix README typo

There's no logic to prevent doubled register entry, but the functional
result is equivalent to if the same key order was typed into vim.

A minor typo in the readme. I've mismemorized the mnemonic for 't' as 'to'
instead of till., but 'to' can't be used as it's a homophone with '2'.
While there was no mistake in the actual logic, it was misleading to use
'to' in the readme.
2023-08-27 21:35:06 +03:00
bobqianic
7e54df414e
whisper : significantly improve the inference quality (#1148)
* Fix MSVC compile error C3688

Instead of simply using 'add_compile_options(/utf-8)' to address the MSVC compile error C3688, a better approach would be to handle it in a way that prevents passing '/utf-8' to NVCC.

* Significantly improve inference quality

In the function `log_mel_spectrogram_worker_thread`, there's an array out-of-bounds issue occurring during the calculation of complex number moduli. This issue is causing disruptions in the FFT spectrum, which, in turn, is reducing the quality of inference.

* Significantly improve inference quality

At last, I've pinpointed the actual source of the problem. Given that the frequency spectrum generated from real input data is symmetrical around the Nyquist frequency, there's a for-loop within the `log_mel_spectrogram_worker_thread` function that attempts to fold the frequency spectrum. Regrettably, a bug within this for-loop is causing a frame shift in the frequency spectrum. The previous attempt to remedy this, which involved using `fft_size + 1` when calculating the modulus, was merely a band-aid solution and did not address the underlying issue.

* Addressed a few minor issues

Fixed the issue of `fft_out` continuously expanding. Resolved the fallback caused by using 'break' instead of `fft_in[j] = 0`.

* Significantly improve inference quality 

Thanks for your patience everyone. It's finally sorted out. Now, the right side of the FFT spectrum is being flipped over to the left, and the amplitudes at corresponding positions on the left and right are added together (the spectrum on the left needs to be shifted by one position), then the average is calculated. FFT_OUT[0] is no longer discarded, making full use of the limited space to pack in more information.

* Add annotation and performance improvement

* Calculate FFT only when fft_in are not all zero

* Some minor performance improvement

* Fixed a bug impacting inference quality

* The first version after all the analysis is completed.

* Fix some bugs and add debug mode

* Fixed several bugs

* Temporarily disable speed-up mode and add debug mode.

* Add debug mode

* Disable speed-up mode and add debug mode

* Fix CI error (#1)

* Fix error

* Fix error

* Fixed several bugs including [BLANK_AUDIO] problem

* Remove Hard-coded hann window

* Some Final Fix (#2)

* Fix error

* Fix error

* Probably the last commit

* Probably the last commit

* whisper : minor coding style changes

* whisper : remove debug from public API

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-08-27 19:51:33 +03:00
junkfood
20a80972f4
whisper.android : migrate from ndk-build to CMake (#1204) 2023-08-27 19:35:16 +03:00
Yunès
7ef3f3837e
main : log probs to text file (#1205)
* token/probability file generated with -ls

* code comment cleaning

* main : indentations

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-08-27 19:09:06 +03:00
Jhen-Jie Hong
a4bb2df36a
quantize : fix load vocab crash when len is 128 (#1160)
* quantize : fix load vocab crash when len is 128

* ci : add quantize job
2023-08-06 11:04:42 +03:00
Duncan McConnell
b948361956
examples : add tinydiarization support for streaming (#1137) 2023-08-03 11:24:07 +03:00
Hrishikesh Barman
925915ae37
whisper : move progress calculation out of whisper.cpp (#1081)
Current `progress_step` was hardcoded into whisper.cpp, this resulted in
bindings having to access progress only at that step even if progress
callback was being called at every iteration.

With this change we get greater granularity progress reporting from
whisper.cpp and bindings/implementations can define their own progress step.
2023-07-25 18:53:34 +03:00
AustinMroz
97f4a7fee0
examples : add Vim plugin (#1131)
* Initial proof of concept Vim plugin

At present, this is likely only slightly better than feature parity with
the existing whisper.nvim

Known issues:
 Trailing whitespace
 Up to an existing length(5 seconds) of speech may be processed when
  listening is enabled
 CPU cycles are spent processing speech even when not listening.

Fixing these issues is likely dependent upon future efforts to create a
dedicated library instead of wrapping examples/stream

* Support $WHISPER_CPP_HOME environment variable

A minor misunderstanding of the whisper.nvim implementation resulted in
a plugin that was functional, but not a drop in replacement as it should
be now.
2023-07-25 18:34:23 +03:00
Georgi Gerganov
4774d2feb0
whisper : minor OpenVINO refactoring (#1037)
Hopefully I didn't break something - haven't tested
2023-07-04 20:28:27 +03:00
Ryan Metcalfe
62b81276e0
whisper : add OpenVINO support (#1037)
* openvino: use OpenVINO encoder inference

* openvino: add python script for OpenVINO model generation

* whisper: Fix 'unused' warnings when OpenVINO isn't enabled in build

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* whisper: Fix compilation error

* whisper: revert whisper_get_openvino_path_encoder & whisper_get_openvino_path_cache to non-const func signatures

* cmake: Add openvino-encoder as separate object target

* whisper : minor style fixes

* minor : indentation fixes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-04 15:56:11 +03:00
Akash Mahajan
c8d0f5fe98
whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize (#1058)
* add HuggingFace mirror to download  ggml model

* support tdrz via simple hack overriding solm tokens

* fix incorrect translate/transcribe token_ids that are not static const

* add apollo 13 sample for tdrz demo

* render [SPEAKER TURN] consistently in all terminal output using vocab.id_to_token

* extend whisper_segment with speaker_turn_next field and save in json output

* fix failing go build

* slipped in some python syntax whoops

* whisper : finalize tinydiarize support (add flag + fixes)

* whisper : tdrz support for word-level timestamps (respect max_len)

* java : try to fix tests after adding tdrz_enable flag

* main : remove TODO leftover

* java : fix params order list after adding "tdrz_enable"

* whisper : fix solm and add nosp token

* main : print tinydiarize help

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-04 09:45:00 +03:00
Georgi Gerganov
fdf58a6668
talk-llama : fix new rope interface 2023-07-03 19:24:01 +03:00
Georgi Gerganov
8ba42095c5
Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)"
This reverts commit 3f7a03ebe3.
2023-07-02 21:53:52 +03:00
Georgi Gerganov
d6509bf78d
ggml : sync latest repo (mostly refactoring changes) 2023-07-02 21:46:09 +03:00
Przemysław Pawełczyk
85ed71aaec
talk-llama : fix build on macOS (#1062)
* talk-llama : use posix_madvise() instead of madvise() derived from BSD

sed -i 's,\<madvise\>,posix_&,g;s,\<MADV_,POSIX_&,g' examples/talk-llama/llama-util.h

* make : enable Darwin extensions for macOS builds

This is an attempt at fixing macOS build error coming from the fact that
RLIMIT_MEMLOCK define is not available there without Darwin extensions.
2023-06-28 22:34:50 +03:00
Przemysław Pawełczyk
3f7a03ebe3
ggml : do not use _GNU_SOURCE gratuitously (#1027)
* Do not use _GNU_SOURCE gratuitously.

What is needed to build whisper.cpp and examples is availability of
stuff defined in The Open Group Base Specifications Issue 6
(https://pubs.opengroup.org/onlinepubs/009695399/) known also as
Single Unix Specification v3 (SUSv3) or POSIX.1-2001 + XSI extensions.

There is no need to penalize musl libc which simply follows standards.

Not having feature test macros in source code gives greater flexibility
to those wanting to reuse it in 3rd party app, as they can build it with
minimal FTM (_XOPEN_SOURCE=600) or other FTM depending on their needs.

It builds without issues in Alpine (musl libc), Ubuntu (glibc), MSYS2.

* examples : include SDL headers before other headers

This is an attempt at fixing macOS build error coming from SDL2 relying
on Darwin extension memset_pattern4/8/16 coming from Apple's string.h.
2023-06-25 16:34:30 +03:00
Przemysław Pawełczyk
62642bb61c
talk-llama : fix build after ggml sync (#1049)
sed -i 's,GGML_BACKEND_CUDA,GGML_BACKEND_GPU,g' examples/talk-llama/llama.cpp
2023-06-25 16:13:50 +03:00
Roddur Dasgupta
f11f33f1c0
models : cd statements are quoted to allow spaces in path (#1041) 2023-06-25 15:27:28 +03:00
Colin
14baf2e7f3
main : add diarization support for all current output types (#1031)
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-25 15:07:57 +03:00
Georgi Gerganov
5feb0dffba
ggml : sync latest ggml lib 2023-06-25 14:30:44 +03:00
faker
598f607e28
main : gracefully exit when invalid params are passed (#1002)
* Refactor whisper_params_parse to return false on failure

* Updated help flag behavior
2023-06-25 13:51:59 +03:00
Nicholas Albion
5b9e59bc07 speak scripts for Windows 2023-06-01 22:45:00 +10:00
geniusnut
ce6f747064
whisper.android : support decode wav file has 2 channels (#972) 2023-05-31 10:13:14 +03:00
DGdev91
5e2b3407ef
examples : update elevenlabs scripts to use official python API (#837)
* Update elevenlabs example to use ufficial python API

* Update elevenlabs example to use official python API
2023-05-24 21:11:01 +03:00
Georgi Gerganov
77eab3fbfe
talk-llama : sync latest llama.cpp (close #922, close #954) 2023-05-23 14:04:39 +03:00
Georgi Gerganov
e410cfc3ce
ggml : sync latest ggml repo
- new Q4 and Q8 quantization
- updated CUDA
2023-05-20 18:56:30 +03:00
Georgi Gerganov
0cb820e0f9
talk-llama : fix build + sync latest llama.cpp 2023-05-14 18:46:42 +03:00
Georgi Gerganov
e693074aa6
ggml : sync latest ggml
- New Q4 and Q5 formats
- Various improvements
2023-05-14 18:04:23 +03:00
Rich Jones
d652cf12ec
main : fix help for --no-timestamps arg (#908) 2023-05-14 17:54:57 +03:00
Jhen-Jie Hong
5300117471
whisper.objc : enable Core ML in example & fix segmentation fault (#910)
* coreml : update endcoder header import path

* coreml : force objc_arc in whisper-encoder.mm

* whisper.objc : create coreml/ group link

* whisper.objc : add coreml model link

* whisper.objc : update readme

* coreml : use -fobjc-arc for coreml/whisper-encoder.mm

* ci: create dummy .mlmodelc for pass ios build

* whisper.objc : update readme

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-05-14 09:47:02 +03:00
Luis Herrera
4e4d00c67a
talk-llama : only copy used KV cache in get / set state (#890)
---------

Co-authored-by: ejones <evan.q.jones@gmail.com>
2023-05-08 20:59:21 +03:00
Luis Herrera
0bf680fea2
talk-llama : fix session prompt load (#854) 2023-05-02 20:05:27 +03:00
CRD716
b806420873
whisper : add detect-language mode (#853)
* add detectlanguage flag

* renaming and help

* no idea why that last one didn't commit

* run language detection if dl is set

* help message fix

* various fixes

* fix quitting

* fix language being english on print
2023-05-02 19:51:52 +03:00
Luis Herrera
be5911a9f3
talk-llama : add --session support (#845)
* feat: adding session support

* readme: adding --session info in examples/talk-llama

* llama: adding session fixes

* readme: updating session doc

* talk-llama: update the value of need_to_save_session to true in order to save the session in the subsequent interaction

* talk-llama: adding missing function which updates session_tokens
2023-05-01 20:18:10 +03:00
Georgi Gerganov
7765770f89
whisper : add memory sizes for Q8_0 (close #846) 2023-05-01 10:03:56 +03:00
Baffin Lee
872a85ae94
whisper.wasm : fix typo in readme (#832) 2023-05-01 09:28:05 +03:00
Georgi Gerganov
c94c469592
whisper : fix quantize bug (#842)
* whisper : debug

* whisper : fix bug during quantization
2023-04-30 22:50:04 +03:00
Georgi Gerganov
4a7d49af95
examples : fix + refactor Levenshtein distance 2023-04-30 19:12:49 +03:00
Georgi Gerganov
794b162a46
whisper : add integer quantization support (#540)
* whisper : add integer quantization support

* examples : add common-ggml + prepare to add "quantize" tool

* whisper : quantization tool ready

* whisper : fix F32 support

* whisper : try to fix shared lib linkage

* wasm : update quantized models to Q5

* bench.wasm : remove "medium" button

* bench.wasm : fix custom model button

* ggml : add Q5_0 and Q5_1 WASM SIMD

* wasm : add quantized models to all WASM examples

* wasm : bump DB version number to 2

* talk-llama : update example to latest llama.cpp

* node : increase test timeout to 10s

* readme : add information for model quantization

* wasm : add links to other examples
2023-04-30 18:51:57 +03:00
Georgi Gerganov
5fd1bdd7fc
whisper : add GPU support via cuBLAS (#834)
* make : add WHISPER_CUBLAS

* make : fix CUBLAS build

* whisper : disable Flash Attention + adjust memory buffers

* whisper : remove old commented code

* readme : add cuBLAS instructions

* cmake : add WHISPER_CUBLAS option

* gitignore : ignore build-cublas
2023-04-30 12:14:33 +03:00
Zollner
5cc17418c7
whisper.android : add some tips (#816) 2023-04-29 11:00:20 +03:00
Laytan Laats
70567eff23
main : escape quotes in csv output (#815) 2023-04-23 19:01:59 +03:00
Taras Glek
02ec83c5d5
stream : flush upon finishing inference (#811) 2023-04-23 17:00:30 +03:00
Philipp Zabel
2bd4b8d577
examples : add missing #include <cstdint> (#798)
common.cpp uses uint8_t and uint64_t, which are defined in <cstdint>.
2023-04-23 16:52:52 +03:00
Tauseef Mohiuddin
eecf2c3d41
main : update escape_double_quotes() function (#776)
Updated the escape_double_quotes() function such that the function now escapes both double quotes and backslashes in the input string.

Changes Made:

- Renamed the function to escape_quotes_and_backslashes

- Modified the condition in the first loop to increment the value of 'escaped_length' for both double quotes and backslashes.

- Modified the condition in second loop to add a backslash before the current character if it is a double quote or a backslash.

Resolves: #769
2023-04-23 16:47:30 +03:00
Georgi Gerganov
f19e23fbd1
whisper : restore decoder temperature fallbacks
I disabled this because there were many complaints about slow decoding.
The current implementation does not allow batching the decoders when
using the "best of" or "beam size" parameters, so the decoding time is
proportional to the number of decoders, which is obviously not great.

However, now there are even more complaints about wrong decodings and
repetition.

So, making a compromise by re-enabling the fallbacks, but defaulting to
just 2 "best of" / "beam size" decoders. Also, the temperature step is
increased from 0.2 to 0.4 - i.e. from maximum of 5 fallbacks to maximum
of 2.

Also, the stream example now has fallbacks enabled by default.

close #471 #477 #508 #612 #719 #731
2023-04-15 16:12:55 +03:00
Bader-eddine Ouaich
2c856fb9e5
whisper : fix potential memory leaks (#740)
* fix potential memory leak if whisper_init_state failed

* fix potential memory leak if gpt2_init failed
2023-04-14 20:05:56 +03:00
Ali Alameh
2c4ac2627d
stream : support language auto-detect (#501)
#445  fix Language auto-detect "auto" flag does not work using the stream tool
2023-04-14 20:02:18 +03:00
DGdev91
001083a769
talk, talk-llama : add basic example script for eleven-labs tts (#728) 2023-04-14 19:53:58 +03:00
Maciek
78548dc03f
talk-llama : correct default speak.sh path (#720)
There is `speak.sh` file in `./examples/talk-llama` as described in README.
However `./examples/talk/speak.sh` is used in `talk-llama.cpp`, this commit corrects that.
2023-04-14 19:36:09 +03:00
LittleLoli
66110dafcc
main : add lrc output support (#718)
* add lrc output support.

* fix wrong comment
2023-04-14 19:35:33 +03:00
Georgi Gerganov
514cd04452 whisper : fix bug in prompt processing (close #705)
Was dereferencing a dangling pointer
2023-04-14 19:17:07 +03:00
Georgi Gerganov
114df388fe
talk-llama : increase context to 2048 2023-04-10 23:09:15 +03:00
Georgi Gerganov
ea36831459
talk-llama : update to latest llama.cpp (improved performance) 2023-04-10 22:59:13 +03:00
InconsolableCellist
5e6e2187a3
talk-llama : fixing usage message for talk-llama (#687)
"-ml" instead of "-mg" for specifying the llama file
2023-03-30 00:10:20 +03:00
Georgi Gerganov
a7f1f33715
main : add <cstring> header 2023-03-29 23:59:45 +03:00
Lucas Zanek
86ecfc6333
whisper.addon : fixed test to new async implementation (#686)
* fixed blocking code on node addon

* modify the example to run async

* format

* added logic to see the whisper output

* added logic to see the whisper output

* removed extra function for more clean example

* fixed whisper test to new async implementation
2023-03-29 23:59:17 +03:00
Egor Egorov
0f759f125d
main : fix typo in JSON output (#648)
* typo in JSON output

* fix double quotes in JSON output
2023-03-29 23:26:39 +03:00
Jhen-Jie Hong
eefed45e37
whisper : add initial_prompt param (#645) 2023-03-29 23:23:23 +03:00
Jonno
21c1e6afc5
whisper.swiftui : update README.md (#682)
- Slight tweaks to README for improved comprehension.
2023-03-29 23:04:38 +03:00
Evan Jones
a47e812a54
talk-llama : add alpaca support (#668) 2023-03-29 23:01:14 +03:00
Georgi Gerganov
e5c197d8aa
talk-llama : add discussion link 2023-03-28 10:11:34 +03:00
Georgi Gerganov
7cd1d3bc34
talk-llama : try to fix windows build .. 2023-03-27 22:40:59 +03:00
Georgi Gerganov
4a0deb8b1e
talk-llama : add new example + sync ggml from llama.cpp (#664)
* talk-llama : talk with LLaMA AI

* talk.llama : disable EOS token

* talk-llama : add README instructions

* ggml : fix build in debug
2023-03-27 21:00:32 +03:00
Lucas Zanek
21165580a1
Nodejs Addon blocking main thread. Implemented Napi::AsyncWorker (#642)
* fixed blocking code on node addon

* modify the example to run async

* format

* added logic to see the whisper output

* added logic to see the whisper output

* removed extra function for more clean example
2023-03-22 22:19:22 +02:00
Jhen-Jie Hong
1d749919e3
whisper.objc : add -O3 -DNDEBUG in release mode (#640) 2023-03-22 22:16:04 +02:00
Leo Moll
8fcd1a3b32
main : provide option for creating JSON output (#615)
* examples : provide option for exporting also as JSON file (ggerganov/whisper.cpp#614)

* main : remove leftovers

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-22 21:37:36 +02:00
Georgi Gerganov
1beff6f66d
models : change HF hosting from dataset to model 2023-03-22 20:44:56 +02:00
Takeshi Inoue
09e9068007
whisper.android : support benchmark for Android example. (#542)
* whisper.android: Support benchmark for Android example.

* whisper.android: update screenshot in README.

* update: Make text selectable for copy & paste.

* Update whisper.h to restore API name

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* whisper.android: Restore original API names.

---------

Co-authored-by: tinoue <tinoue@xevo.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-07 21:36:30 +02:00
venkr
b597c5a779
qual-bench.sh : add quality comparison tool, and update main.cpp to allow using a font file (#569) 2023-03-06 19:18:11 +02:00
Takeshi Inoue
a3fb6c507f
whisper.android : enable fp16 instrinsics (FP16_VA) which is supported by ARMv8.2 or later. (#572) 2023-03-06 19:15:57 +02:00
sandrohanea
59fdcd19c8
whisper : add whisper_state + default state on the whisper_context (#523)
* Added whisper state + default state on the whisper_context

* Fixed some examples and bindings

* Fixed whisper_n_len (which was used in some binding) and added whisper_n_len_from_state

* Fixed comments

* whisper : reuse kv_cache_free() and fix compiler warnings

* whisper : clean-up the API comments

---------

Co-authored-by: Sandro Hanea <sandrohanea@microsoft.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-05 21:42:19 +02:00
Georgi Gerganov
478289a4b3
whisper : set no_context == true by default (#537) 2023-03-05 20:53:43 +02:00
HY. Kelvin Lee
72af0f5697
main : add csv header (#552) 2023-03-02 18:32:16 +02:00
Georgi Gerganov
f254e78737
yt-wsp.sh : print help on empty args 2023-02-18 09:42:31 +02:00
conradg
69e6e4644a
main : fix std in input (#503)
if we don't add this as an explicit check, then we get an "error: unknown argument: -" later on
2023-02-15 19:31:16 +02:00
Georgi Gerganov
09d7d2b68e
examples : refactor in order to reuse code and reduce duplication (#482)
* examples : refactor common code into a library

* examples : refactor common SDL code into a library

* make : update Makefile to use common libs

* common : fix MSVC M_PI ..

* addon.node : link common lib
2023-02-15 19:28:10 +02:00
genevera (she/her)
459753342d
yt-wsp.sh : add unique filename generation (#495)
Co-authored-by: genevera <genevera@noreply.users.github.com>
2023-02-14 20:12:51 +02:00
Qianhe Chen
ab1916fc59
ci : add node addon test and optimize compilation configuration (#468)
* addon: implement node addon call whisper through cpp

* addon: modify the license to MIT

* addon: remove iostream

* addon: rename dir

* addon: fix typo

* addon: configure cmake to build when cmake-js is used

* ci: add addon.node test ci

* addon: remove build WHISPER_BUILD_TESTS

* addon: update build command

* addon: add test

* addon: add test file

* addon: adapt to compile on Windows

* addon: fix typo

* addon: reuse jfk.wav

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* addon: reuse jfk.wav

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-02-05 15:02:08 +02:00
Matija Pevec
d012b5c7e4
whisper : add "split_on_word" flag when using using "max_len" option (#455)
* Update whisper.cpp

* fix: trim function

* feat: added flag to split on word

* fix: arguments for main
2023-02-05 14:44:23 +02:00
Georgi Gerganov
f3ee4a9673
whisper : reduce memory usage during inference (#431)
* ggml : add "scratch" buffer support

* ggml : support for scratch ring-buffer

* ggml : bug fix in ggml_repeat()

* ggml : error on scratch buffer overflow

* whisper : use scratch buffers during inference (base model only)

* whisper : update memory usage for all models

* whisper : fix encoder memory usage

* whisper : use whisper_context functions instead of macros

* whisper : fix FF + remove it from README

* ggml : reuse ggml_new_i32

* ggml : refactor the scratch buffer storage

* whisper : reorder scratch buffers in the decoder

* main : add option to disable temp fallback

* Update README.md
2023-02-04 09:45:52 +02:00
Qianhe Chen
c306a7fd89
addon.node : using whisper as a Node.js addon (#443)
* addon: implement node addon call whisper through cpp

* addon: modify the license to MIT

* addon: remove iostream

* addon: rename dir

* addon: fix typo

* addon: configure cmake to build when cmake-js is used
2023-02-04 09:10:25 +02:00
Taisei Mima
86ef64a855
wasm : fix typo in helper.js (#459) 2023-02-04 08:49:15 +02:00
Alex Bacart
3b1960520a
main : CSV format export trimmed spaces fix (#444)
* Update main.cpp

Removed string trimming

* Update main.cpp

* Update main.cpp

* Revert "Update main.cpp"

This reverts commit d8924fdcfe.

* Revert "Update main.cpp"

This reverts commit 252e508d85.
2023-02-04 08:48:35 +02:00
Eric Tendian
47737b2e82
livestream.sh : run main with model arg instead of default (#453)
Actually utilizes the $model var when calling ./main.
2023-01-27 01:13:31 +02:00
Georgi Gerganov
60337f5306
wasm : check if navigator.storage.estimate() is available
Safari does not support it
2023-01-25 20:00:59 +02:00
Ondrej Kokes
11f61cecd6
whisper.wasm : add labels for easier radio selection (#435) 2023-01-23 20:49:00 +02:00
Georgi Gerganov
f583e2d2f5
main : we had accidentally disabled the temperature fallback .. (#291) 2023-01-18 22:51:41 +02:00
Georgi Gerganov
206fc93396
whisper.wasm : add small and small.en models 2023-01-18 21:58:55 +02:00
Chia-Hsiang Cheng
472a473fd1
main : add an option to accept optional output filenames (#424)
* Add an option to accept optional output filenames

* Format the file

Co-authored-by: Chia-Hsiang Cheng <gary.chiahsiang.cheng@gmail.com>
2023-01-18 21:26:31 +02:00
Georgi Gerganov
9ba66c2fad
stream : fix handling of --step == --length (#416) 2023-01-18 21:22:52 +02:00
Georgi Gerganov
1ccb8a46a5
bench : fix Windows linkage by moving ggml benches in whisper lib .. 2023-01-18 21:19:50 +02:00
Georgi Gerganov
1290fc6457
bench : add memcpy and ggml_mul_mat benchmarks 2023-01-18 20:31:46 +02:00
Digipom
49b529ba74
whisper.android : add support for loading directly from asset in C (#415) 2023-01-16 21:57:35 +02:00
Georgi Gerganov
c9aeb33676
stream : fix --keep_context argument to be used correctly (#354) 2023-01-16 19:37:40 +02:00
Georgi Gerganov
c3991bbb24
Update README.md 2023-01-15 14:08:12 +02:00
Georgi Gerganov
fafd78945d
bench.wasm : print system info 2023-01-15 11:34:03 +02:00
Georgi Gerganov
8de452c18b
Improve decoding (#291)
* whisper : prepare infra for new decoding strategies

* whisper : apply logit filters and compute logprobs

* whisper : add whisper_get_logits()

* whisper : separate self and cross attention memory

Initial step needed for supporting parallel decoders

* whisper : move probs_id buffer to whisper_context

* whisper : refactor kv cache into separate struct

* whisper : move self-attention kv cache to whisper_decoder

* whisper : wip decoding parameters + strategies

* whisper : wip decoding parameters + strategies (part 2)

* whisper : wip decoding parameters + strategies (part 3)

* whisper : wip decoding parameters + strategies (part 4)

* whisper : fix prompt_past update to not include prompt_init

* whisper : temperature + best_of support

* whisper : support for compression_ration_threshold

We actually use entropy, but it is similar

* command : fix example to use logits instead of obsolete probs

* whisper : handle empty sequence ranking

* whisper : add WHISPER_DEBUG + diagnostic prints + new main args

* whisper : minor fixes

* whisper : add beam-search support

* whisper : bug fix when there no previous context

* whisper : add comments

* stream : disable temperature fallback

For real-time processing, we always want a single decoder running at T=0

* whisper.swiftui : update example - fix paths + add empty folders
2023-01-15 11:29:57 +02:00
Georgi Gerganov
a6dbd9188b
stream : fix a bug that inserted a lot of empty audio at the start
The quality was terrible due to this
2023-01-14 19:20:47 +02:00
Syahmi Azhar
1512545149
whisper : add loader class to allow loading from buffer and others (#353)
* whisper : add loader to allow loading from other than file

* whisper : rename whisper_init to whisper_init_from_file

* whisper : add whisper_init_from_buffer

* android : Delete local.properties

* android : load models directly from assets

* whisper : adding <stddef.h> needed for size_t + code style

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-01-08 13:03:33 +02:00
Georgi Gerganov
52a3e0c92a
ggml : improve vec_dot_f16 unrolling in flash_attn_f16 2023-01-08 11:41:18 +02:00
Georgi Gerganov
d1ea1220ff
command : clean-up / refactoring / formatting (#383) 2023-01-07 21:43:24 +02:00
David
9c4a1522f6
command : always-prompt mode (#383) 2023-01-07 21:41:11 +02:00
Georgi Gerganov
87dd4a3081
talk.wasm : bump memory usage + update whisper.js 2023-01-06 21:13:44 +02:00
Georgi Gerganov
6b351bb669
command : add "guided-mode" video demo in the README.md 2023-01-06 18:59:26 +02:00
Georgi Gerganov
b3c865083e
ci : add emscripten build 2023-01-05 22:10:20 +02:00
Georgi Gerganov
a0d4f8e65c
main : make whisper_print_segment_callback() more readable (close #371) 2023-01-05 21:45:05 +02:00
Georgi Gerganov
196d738974
minor : close #370 + Makefile build info print change 2023-01-05 21:35:45 +02:00
Andy Maloney
84c6b42e65
cmake : update to 3.19 (#351)
- update from 3.0 (from 2014) to 3.19 (from 2020)
- move some global setting onto the targets (through a cmake include)
2023-01-05 21:22:48 +02:00
Georgi Gerganov
a466c3404d
stream : fix data race on bool + avoid division-by-zero 2023-01-02 10:20:50 +02:00
Andy Maloney
f00509d57c
command : refactor to split command list & general transcription modes (#331)
This makes it easier to understand if you're looking for only one of the capabilities.
2022-12-31 14:08:57 +02:00
Niels Mayer
a593b932e4
main : add -ocsv, aka --output-csv to output a CSV file
Adds -ocsv, aka --output-csv feature to examples/main, which outputs a CSV file containing lines formatted as follows <startTime-in-integer-milliseconds>, <endTime-in-integer-milliseconds>, "<transcript-line-including-commas>".
2022-12-29 14:04:00 +02:00
Andy Maloney
331c0bbddc
examples : fix memory leak on failure to load gpt2 model (#323) 2022-12-23 20:19:07 +02:00
Andy Maloney
dc90efd504
examples : small code cleanups (#322)
- remove unnecessary initialization of string to ""
- use empty() instead of checking size()
- use emplace_back instead of push_back
- use nullptr instead of NULL
- remove unnecessary call to .data() on string
- use character overload of find_first_of() instead of passing a string
2022-12-23 20:18:51 +02:00
Digipom
0f4227d9ee
examples : add whisper.swiftui demo app (#308)
* Add SwiftUI demo project.

* Add -DGGML_USE_ACCELERATE
2022-12-23 10:56:18 +02:00
Kevin Brothaler
91fc08c641 Build a vfpv4 library for armeabi-v7a and do runtime detection to select the right library 2022-12-22 16:47:54 +02:00
Kevin Brothaler
e1432dd91a Check for both __ARM_NEON and __ARM_FEATURE_FMA so that the project can be compiled for armv7a.
Android armeabi-v7a's NEON support doesn't support FMA unless configured with `-mfpu=neon-fp-armv8`, which would need runtime checks.
* Also removed ABI filter from Android project.
2022-12-22 16:47:54 +02:00
Kevin Brothaler
22193cbfe8 Bump NDK version 2022-12-22 16:47:54 +02:00
Georgi Gerganov
90564f85f9
Update README.md 2022-12-19 22:09:21 +02:00
Georgi Gerganov
99da1e5cc8
cmake : enable and fix -Wall -Wextra -Wpedantic C++ warnings 2022-12-19 20:45:08 +02:00
Matheus de Sousa
8e3f129b4d
minor : resolves some of warnings when compiling with clang/clang++ (#294)
* Resolves some of warnings when compiling with clang/clang++

Mostly nit stuff that clang catches when compiling with -Wall -Wextra
-pedantic.

- Fix comparison between sign/unsigned integers.
- Passes a constant reference (const&) instead of copying each time.

* minor : normalize coding style

* minor : fix warning

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2022-12-19 20:19:01 +02:00
Georgi Gerganov
fba10a4c68 whisper : language auto-detect (#59) 2022-12-17 18:49:44 +02:00
Georgi Gerganov
32fbc8cd04
main : add option to print the progress (#276) 2022-12-16 20:20:43 +02:00
Georgi Gerganov
b8065d90f5
main : add "--prompt" command line argument (#90)
This allows to provide an initial prompt to be used at the start of the
processing.
2022-12-16 19:43:16 +02:00
Georgi Gerganov
4312995974 command : better indentation 2022-12-16 19:38:18 +02:00
Georgi Gerganov
5eeeb3412d command : update README, show how to use guided mode 2022-12-16 19:38:18 +02:00
Georgi Gerganov
6a69e3ae27 command : adding guided mode 2022-12-16 19:38:18 +02:00
Georgi Gerganov
ea19ed33f1
Update README.md (#46)
Add references to the new Android app
2022-12-16 19:28:51 +02:00
Digipom
675e787171
Add Android sample (#277)
* Add Android sample

* Use main project C files

* Stop existing playback before starting new playback

* Make text scrollable

* Stop playback when starting to record

* Remove extra var
2022-12-16 19:20:13 +02:00
Georgi Gerganov
a82d331034
stream : update README.md + comments 2022-12-16 18:04:19 +02:00
Georgi Gerganov
5a5c5ddcca
Update README.md 2022-12-15 20:38:08 +02:00
Georgi Gerganov
34e0b4b9ef
stream : fix build 2022-12-15 20:15:36 +02:00
Georgi Gerganov
b0f8013eb9
stream : add sliding window mode 2022-12-15 19:59:17 +02:00
Georgi Gerganov
a613f16aec
talk : improve prompting 2022-12-12 23:44:36 +02:00
Georgi Gerganov
f309f97df6
Node.js package (#260)
* npm : preparing infra for node package

* npm : package infra ready

* npm : initial version ready

* npm : change name to whisper.cpp

whisper.js is taken
2022-12-12 20:17:27 +02:00
Georgi Gerganov
aa6adda26e
talk : make compatible with c++11 (part 2) 2022-12-11 20:34:04 +02:00
Georgi Gerganov
444349f4ec
talk : make compatible with c++11 2022-12-11 20:19:17 +02:00
Lexevolution
6ed786957e
Add newline per segment for text output (#254) 2022-12-11 20:00:29 +02:00
Georgi Gerganov
fcf515de60
bench.wasm : same as "bench" but runs in the browser (#89) 2022-12-11 11:09:10 +02:00
Georgi Gerganov
85c9ac18b5
Update README.md 2022-12-10 16:54:57 +02:00
Georgi Gerganov
b7c85d1ea6 talk : fix build for MSVC 2022-12-10 16:51:58 +02:00
Georgi Gerganov
3b1aacbe6d talk : talk with AI in the terminal 2022-12-10 16:51:58 +02:00
Georgi Gerganov
56822621a8 twitch.sh : various fixes and polishing
- check if streamlink is installed
- fix audio chunking
- change default threads to 4
2022-12-08 19:20:04 +02:00
keyehzy
9e5f3ddc16 Allow for Twitch.tv live transcription
We rely on streamlink library to give us a stream, then we proceed similarly to
the radio livestream example.
2022-12-08 19:20:04 +02:00
Georgi Gerganov
47afb93c3c
yt-wsp.sh : improve usage instructions 2022-12-07 22:12:08 +02:00
Georgi Gerganov
575c53dc41
yt-wsp.sh : fix usage instruction + comment 2022-12-07 21:12:55 +02:00
Georgi Gerganov
faa85f9840 livestream.sh : remove obsolete comment 2022-12-07 04:41:43 +02:00
Georgi Gerganov
9fe7306f4b
models : add the new "large" model release by OpenAI
The old "large" model is now renamed "large-v1".
If you have been using it, make sure to rename it and download the new
"large" model for best results.
2022-12-06 18:48:57 +02:00
Georgi Gerganov
57e0e6b700
livestream : handle ffmpeg errors gracefully and stabilize transcript 2022-12-01 20:49:09 +02:00
Georgi Gerganov
4f7363077f
livestream : minor changes 2022-12-01 19:47:58 +02:00
semiformal-net
093c840dee
livestream : fix losing words across audio chunk (#195)
* improve livestream script

* Update examples/livestream.sh

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

Co-authored-by: Paul Edwards <paul.edwards@semiformal.net>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2022-12-01 19:18:22 +02:00
Georgi Gerganov
4698dcdb52 whisper : add mechanism for aborting the whisper_full() computation 2022-11-27 20:42:45 +02:00
Georgi Gerganov
164df0d447
whisper.objc : fix context + broken readme links 2022-11-27 10:52:27 +02:00
Georgi Gerganov
e266cb0723
whisper.objc : add real-time processing (#97)
Similar to the "stream" app
2022-11-26 18:32:46 +02:00
Georgi Gerganov
c207eed431
whisper.objc : fix build warnings 2022-11-26 16:27:04 +02:00
Georgi Gerganov
a425365b82
yt-wsp.sh : script to easily transcribe VODs
Thanks to @DaniruKun
ref: https://gist.github.com/DaniruKun/96f763ec1a037cc92fe1a059b643b818

Usage:

  cd whisper.cpp
  make

  ./examples/yt-wsp.sh <video-url>
2022-11-26 12:54:42 +02:00
Georgi Gerganov
68ecadbbc9
command.wasm : add voice assistant example for the Web (#171)
Same as the command-line tool "command", but runs in the browser

Also, added helper script "extra/deploy-wasm.sh" and fixed some timing
constants for the WASM examples.
2022-11-26 11:40:06 +02:00
Georgi Gerganov
c536ff4005
minor : add comment for using "generate_karaoke.sh" 2022-11-26 10:22:42 +02:00
Georgi Gerganov
cb70b07db5
livestream.sh : simple tool to transcribe audio livestreams (#185) 2022-11-26 10:05:37 +02:00
Georgi Gerganov
3c390ffe38
stream.wasm : add web-based real-time transcription (#112) 2022-11-25 23:57:46 +02:00
Georgi Gerganov
be16dfa038
whisper.wasm : do not block page while processing (close #86) 2022-11-25 23:07:42 +02:00
Georgi Gerganov
0f619b52ce
main : add stereo-channel-based diarization (#64)
Not tested - I don't have stereo dialog audio
2022-11-25 22:08:58 +02:00
Georgi Gerganov
1246dd023e
command : add demonstration video 2022-11-25 20:23:58 +02:00
Georgi Gerganov
0be27bbd92
command : fix build + fix README + add bold printing 2022-11-25 19:53:50 +02:00
Georgi Gerganov
bc88eb13c6
examples : add "command" tool (#171) 2022-11-25 19:36:57 +02:00
Georgi Gerganov
b8ce25dec1
refactoring : more readable code 2022-11-25 19:28:04 +02:00
Georgi Gerganov
e4805d9601
wasm : refactor wasm example + reuse fetch mechanism 2022-11-24 23:13:26 +02:00
Georgi Gerganov
ff36415a86
talk.wasm : update video link + some minor fixes 2022-11-24 20:15:24 +02:00
Georgi Gerganov
025ff465b6
Update README.md
Use a less cringy video to demo talk.wasm lol
2022-11-24 20:09:45 +02:00
Georgi Gerganov
abce28ea99
talk.wasm : move to https://whisper.ggerganov.com/talk
This way, we can share the same models across different WASM examples
and not have to download them for each page
2022-11-24 18:24:06 +02:00
Georgi Gerganov
454b91de16
main : fix dangling pointer when using stdin for input (#65) 2022-11-24 17:53:51 +02:00
Georgi Gerganov
d7024cf9dc
main, stream : remove --verbose flag (#178) 2022-11-24 17:52:04 +02:00